>>I am sorry Bryan but we seem to have some misunderstanding. >>3ware is on Intel 7500 motherboards. > > > Really? You can get an Intel E7500 chipset with 3Ware? Argh...why would I need a riser if the 3ware were onboard? The 3ware was attached to the board via a PCI-X riser card. I meant the 3ware + Intel 7501 board + PCI-X riser card fiasco. > Cool! Which models? Sorry, misunderstanding. > Seems like the typo bug is going around. ;-> > [ Okay, I admit, I hold the record -- by a wide margin ] > > >>Nforce4 Ultra and above support command queueing according >>to them. > > > They wish. ;-> Eh? http://www.nvidia.com/object/IO_16450.html They specifically highlight NCQ on page 4 for their SATA implementation. > > Then again, the ATA "controller" is rather "dumb" -- the NCQ > is on the IDE of the end-device. It's not like SCSI where > there's an intelligent, hardware host. Well, they are not talking about ATA...they are talking about SCSI like tag command queueing on their SATA side of things, you know, Native Command Queueing. No, not NForce 2 or 3 or 4 but Nforce 4 Ultra and above (Nforce4 SLI, Nforce Pro 2xxx) > > The AHCI is supposed to be the software/host equivalent of > controlling up to 32 ATA devices with commands, etc... But I > haven't seen much work well in that regard on even Windows. > > >>Yes...where possible. Their SATA/NCQ implementation >>apparently does not allow them to provide specs or > > something. > > Really? Hmmm, I thought the libata guys were pretty happy > with them. I could be wrong, as it's been 2nd hand > commentary. > > > Jeff does not get anything. He does not list Nvidia implementations of their SATA controllers as 'open' like the Intel AHCI and Silicon Image 3112 among others.